CUDA使用运行时API查询设备信息

1.  在CUDA运行时API中有很多函数可以帮助管理这些设备，使用这些运行时API查询设备信息，代码如下：

#include <stdio.h>
#include <stdlib.h>
#include <cuda_runtime.h>
#include <math.h>

#define EXIT_FAULLURE -1
#define EXIT_SUCCESS 1

int main(int argc, char **argv[])
{
	printf("%s Starting... \n\n", argv[0]);

	int deviceCount;
	cudaError_t error_id = cudaGetDeviceCount(&deviceCount);
	if (error_id != cudaSuccess)
	{
		printf("cudaGetDeviceCount returned %d\n -> %s\n", (int)error_id, cudaGetErrorString(error_id));
		printf("Result = FALL\n");
		exit(EXIT_FAULLURE);
	}
	if (deviceCount == 0)
	{
		printf("There are no available device(s) that support CUDA\n");
	}
	else
	{
		printf("Deltected %d CUDA Capable device(s)\n", deviceCount);
	}
	int dev, driverVersion = 0, runtimeVersion = 0;
	dev = 0;
	cudaSetDevice(dev);
	cudaDeviceProp deviceProp;
	cudaGetDeviceProperties(&deviceProp, dev);
	printf("Device %d: \"%s\"\n", dev, deviceProp.name);	
	cudaDriverGetVersion(&driverVersion);
	cudaRuntimeGetVersion(&runtimeVersion);
	printf("CUDA Driver Version / Runtime Version %d.%d / %d.%d\n",
		driverVersion / 1000, (driverVersion % 100) / 10, 
		runtimeVersion / 1000, (runtimeVersion % 100) / 10);
	printf("CUDA Capability Major/Minor version number:	%d.%d\n",
		deviceProp.major, deviceProp.minor);
	printf("Total amount of global memory: %2.f MBytes (%llu bytes\n)",
		(float)deviceProp.totalGlobalMem / (pow(1024.0, 3)),(unsigned long long) deviceProp.totalGlobalMem);
	printf("GPU Clock rate: %.0f MHz (%0.2f GHz)\n",
		deviceProp.clockRate * 1e-3f, deviceProp.clockRate * 1e-6f);
	printf("Memory Clock rate: %.0f Mhz\n",
		deviceProp.memoryClockRate * 1e-3f);
	printf(" Memory Bus Width: %d-bit\n",
		deviceProp.memoryBusWidth); 	
	if (deviceProp.l2CacheSize)
	{
		printf(" L2 Cache Size: %d bytes\n",deviceProp.l2CacheSize);
	}
	printf(" Max Texture Dimension Size (x,y,z) 1D = (%d), 2D = (%d, %d), 3D = (%d, %d, %d)\n",
		deviceProp.maxTexture1D, deviceProp.maxTexture2D[0], deviceProp.maxTexture2D[1],
		deviceProp.maxTexture3D[0], deviceProp.maxTexture3D[1], deviceProp.maxTexture3D[2]);
	printf(" Max Layered Texture Size (dim) x layers 1D=(%d) x %d, 2D=(%d,%d) x %d\n",
		deviceProp.maxTexture1DLayered[0], deviceProp.maxTexture1DLayered[1], deviceProp.maxTexture2DLayered[0],
		deviceProp.maxTexture2DLayered[1], deviceProp.maxTexture2DLayered[2]); 
	printf("Total amount of constant memory: %lu bytes\n", deviceProp.totalConstMem);
	printf("Total amount of shared memory per block:  %lu bytes\n", deviceProp.sharedMemPerBlock);
	printf("Total number of registers available per block: %d\n", deviceProp.regsPerBlock);
	printf("Warp size: %d\n", deviceProp.warpSize);
	printf("Maximum number of threads per mult iprocessor:  %d\n", deviceProp.maxThreadsPerMultiProcessor);
	printf("Maximum number of threads per block:  %d\n", deviceProp.maxThreadsPerBlock); 
	printf("Maximum sizes of each dimension of a block:  %d x %d x %d\n",
			deviceProp.maxThreadsDim[0], deviceProp.maxThreadsDim[1], deviceProp.maxThreadsDim[2]);
	printf("Maximum sizes of each dimension of a grid:  %d x %d x %d\n",
		deviceProp.maxGridSize[0], deviceProp.maxGridSize[1], deviceProp.maxGridSize[2]);
	printf("Maximum memory pitch %lu bytes\n", deviceProp.memPitch);
	exit(EXIT_SUCCESS);

	return 0;
}

2. 其中， cudaDeviceProp 结构定义如下：

// cudaDeviceProp 结构定义如下:

struct cudaDeviceProp {
	char name[256]; // 用于标识设备的ASCII字符串;
	size_t totalGlobalMem; // 设备上可用的全局存储器的总量
	size_t sharedMemPerBlock; // 线程块可以使用的共享存储器的最大值,多处理器上的所有线程块可以同时共享这些存储器
	int regsPerBlock; // 线程块可以使用的32位寄存器的最大值,多处理器上的所有线程块可以同时共享这些寄存器
	int warpSize; // 按线程计算的warp块大小
	size_t memPitch; // 允许通过cudaMallocPitch()为包含存储器区域的存储器复制函数分配的最大间距(pitch)
	int maxThreadsPerBlock; // 每个块中的最大线程数
	int maxThreadsDim[3]; // 块各个维度的最大值
	int maxGridSize[3]; // 网格各个维度的最大值
	size_t totalConstMem; // 设备上可用的不变存储器总量
	int major; // 定义设备计算能力的主要修订号
	int minor; // 定义设备计算能力的次要修订号
	int clockRate; // 时钟频率
	size_t textureAlignment; // 对齐要求;与textureAlignment字节对齐的纹理基址无需对纹理取样应用偏移;
	int deviceOverlap; // 如果设备可在主机和设备之间并发复制存储器,同时又能执行内核,则此值为 1;否则此值为 0;
	int multiProcessorCount; // 设备上多处理器的数量
}

3. 运行结果，如下：